10068327

Method and System for Statistical Modeling of Data Using a Quadratic Likelihood Functional

PublishedSeptember 4, 2018
Assigneenot available in USPTO data we have
InventorsAmos YAHIL
Technical Abstract

Patent Claims
20 claims

Legal claims defining the scope of protection, as filed with the USPTO.

1

1. A computer-implemented method for removing noise from a signal of a target object, the computer-implemented method comprising: receiving an input signal from a source system, the input signal comprising image data identifying a target object and a plurality of parameters, and further comprising a noise portion, wherein the image data is selected from a group consisting of X-ray, CT, emission tomography, SPECT and PET, and the target object comprises image data of a body part of a patient; selecting an initial subset of parameters from the plurality of parameters; estimating a nonparametric probability distribution function (pdf) from the received input signal which comprises a linear combination of functions; generating a quadratic likelihood function (QLF) based on the nonparametric PDF estimated including the linear combination of functions; determining a fit of the initially selected subset of parameters to the data identifying the target object, based on the QLF; in response to the determined fit of the initially selected subset of parameters being below a predetermined threshold, iteratively optimizing parameters by selecting a new subset of parameters from the plurality of parameters and determining a fit of the new subset of parameters, until the determined fit satisfies the predetermined threshold; and generating an output signal comprising a reconstructed signal of the target object constructed using the new subset of iteratively optimized parameters.

2

2. The computer-implemented method of claim 1 , wherein the data comprises weights w i and the QLF has the form L = ∫ d ⁢ ⁢ x [ 1 2 ⁢ f ⁡ ( x ) 2 - f ⁡ ( x ) ⁢ ∑ i ⁢ w i ⁢ δ ⁡ ( x - x i ) ] .

3

3. The computer-implemented method of claim 1 , further comprising calculating a source term using the data and basis functions.

4

4. The computer-implemented method of claim 3 , wherein the QLF is obtained by: computing a Gram matrix using the basis functions; and combining the Gram matrix, the parameters and the source tem′ to produce the QLF.

5

5. The computer-implemented method of claim 1 , wherein the output comprises a 2D, 3D, or 4D image representation of the target object displayed at a graphical user interface.

6

6. The computer-implemented method of claim 1 , wherein the image data is taken in at least two planes, and wherein the output comprises a 3D representation.

7

7. The computer-implemented method of claim 1 , wherein the image data is taken in a least two planes and further comprises time, and wherein the output comprises a 4D representation.

8

8. A system for modeling of data describing a target object contained in an input signal, the system comprising: a computer-readable medium; a parameter optimization processor coupled to the computer-readable medium; and a communication interface coupled to the parameter optimization processor and adapted to receive and transmit electronic representations of reconstructed models signals to and from the parameter optimization processor, respectively, the computer-readable medium having stored thereon software instructions that, when executed by the parameter optimization processor, cause the parameter optimization processor to perform operations including: receive the input signal from a source system configured to collect object data, the input signal comprising image data identifying a target object and a plurality of parameters, and further comprises noise, wherein the image data is selected from a group consisting of X-ray, CT, emission tomography, SPECT and PET, and the target object comprises image data of a body part of a patient; select an initial subset of parameters corresponding to the target object from the plurality of parameters; estimate a nonparametric probability distribution function comprising (pdf) from the received input signal which comprises a linear combination of functions; generate a quadratic likelihood function (QLF) based on the nonparametric PDF including the linear combination of functions; determine a fit of the initially selected subset of parameters to the data identifying the target object, based on the QLF; in response to the determined fit of the initially selected subset of parameters being below a predetermined threshold, iteratively optimize parameters by selecting a new subset of parameters from the plurality of parameters and determining a fit of the new subset of parameters, until the determined fit satisfies the predetermined threshold; and generate an output signal comprising a signal of the target object constructed using the new subset of iteratively optimized parameters.

9

9. The system of claim 8 , wherein the data comprises weights w; and the QLF has the form L = ∫ d ⁢ ⁢ x [ 1 2 ⁢ f ⁡ ( x ) 2 - f ⁡ ( x ) ⁢ ∑ i ⁢ w i ⁢ δ ⁡ ( x - x i ) ] .

10

10. The system of claim 8 , further comprising calculating a source term using the data and basis functions.

11

11. The system of claim 10 , wherein the QLF is obtained by: computing a Gram matrix using the basis functions; and combining the Gram matrix, the parameters and the source term to produce the QLF.

12

12. The system of claim 8 , wherein the output signal comprises a 2D, 3D or 4D image representation of the target object displayed at a graphical user interface.

13

13. The system of claim 8 , wherein the image data is taken in at least two planes, and wherein the output comprises a 3D representation.

14

14. The system of claim 8 , wherein the image data is taken in a least two planes and further comprises time, and wherein the output comprises a 4D representation.

15

15. A method of generating a reconstructed image of a target object from an input signal having a data component and a noise component, the method comprising: receiving the input signal from an image source system, the input signal comprising image data identifying a target object and a plurality of parameters, and further comprising a noise portion, wherein the image data is selected from a group consisting of X-ray, CT, emission tomography, SPECT and PET, and the target object comprises image data of a body part of a patient; selecting an initial subset of parameters from the plurality of parameters; estimating a nonparametric probability distribution function (pdf) from the received input signal which comprises a linear combination of functions; generating a quadratic likelihood function (QLF) based on the nonparametric PDF including the linear combination of functions; determining a fit of the initially selected subset of parameters to the data identifying the target object, based on the QLF; in response to the determined fit of the initially selected subset of parameters being below a predetermined threshold, iteratively optimizing parameters by selecting a new subset of parameters from the plurality of parameters and determining a fit of the new subset of parameters, until the determined fit satisfies the predetermined threshold; and generating an output signal comprising a display of reconstructed image of the target object based on the new subset of iteratively optimized parameters.

16

16. The method of claim 15 , wherein the input signal comprises first plane image data and second plane image data, and the output comprises displaying a three-dimensional image of the target object.

17

17. The method of claim 16 , wherein the data comprises weights w; and the QLF has the form L = ∫ d ⁢ ⁢ x [ 1 2 ⁢ f ⁡ ( x ) 2 - f ⁡ ( x ) ⁢ ∑ i ⁢ w i ⁢ δ ⁡ ( x - x i ) ] .

18

18. The method of claim 15 , further comprising calculating a source term using the data and basis functions.

19

19. The method of claim 18 , wherein the QLF is obtained by: computing a Gram matrix using the basis functions; and combining the Gram matrix, the parameters and the source term to produce the QLF.

20

20. The computer-implemented method of claim 1 , wherein the QDF comprises a form L = ∫ d ⁢ ⁢ x [ 1 2 ⁢ f ⁡ ( x , θ ) 2 - f ⁡ ( x , θ ) ⁢ ∑ i ⁢ δ ⁡ ( x - x i ) ] ⁢ where θ represents the parameters, x represents the positions of the observations, and f (x, θ) is the pdf.

Patent Metadata

Filing Date

Unknown

Publication Date

September 4, 2018

Inventors

Amos YAHIL

Want to explore more patents?

Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.

Citation & reuse

Analysis on this page is generated by Patentable — an AI-powered patent intelligence platform. AI-generated summaries, explanations, and analysis may be reused with attribution and a visible link back to the canonical URL below. Patent abstracts and claims are USPTO public domain.

Cite as: Patentable. “METHOD AND SYSTEM FOR STATISTICAL MODELING OF DATA USING A QUADRATIC LIKELIHOOD FUNCTIONAL” (10068327). https://patentable.app/patents/10068327

© 2026 Patentable. All rights reserved.

Patentable is a research and drafting-assistant tool, not a law firm, and does not provide legal advice. Documents we generate are drafts for review by a licensed patent attorney.